Gemini Robotics 2 brings whole body intelligence to robots
Gemini Robotics 2 brings whole body intelligence to robots
Google DeepMind has released Gemini Robotics 2, a new model that enables robots to perform complex tasks with whole-body intelligence, advanced dexterity, and multi-robot collaboration. The model supports real-time reasoning, on-device adaptation, and safety features for human-robot interaction.
Google DeepMind introduces Gemini Robotics 2, a significant advancement in whole-body control and multi-robot collaboration for embodied AI. The release highlights improvements in dexterity, reasoning, and on-device adaptation, with a focus on safety and real-world task execution.
Evidence and limits
Published automatically after robotics and source-evidence checks; no manual editorial approval is recorded. Source assertions are not independently verified. Missing information remains not reported.
- Environment:
- Not reported
- Control:
- Not reported
- Data origin:
- Not reported
Source excerpts and review record
No manual editorial approval recorded.
Original source quotation: “From feet to fingertips — we are teaching robots intelligent whole-body control, fine dexterity, and teamwork to complete a broad range of complex tasks”
Source E1
Original source quotation: “Most robots are pre-programmed or teleoperated for narrow, repetitive task sequences”
Source E2
Original source quotation: “We demonstrated how Gemini's multimodal understanding could drive real-world action with Gemini Robotics”
Source E3
Original source quotation: “Gemini Robotics 2 enables robots to reason through every movement, unlocking a broad range of tasks”
Source E4
Original source quotation: “It can even team up with other robots to finish the job faster”
Source E5
Original source quotation: “Gemini Robotics On-Device 2 is built specifically to handle these constraints — it is our most-efficient vision-language-action model (VLA) optimized to run locally on robotic devices”
Source E6
Original source quotation: “This model is natively multi-embodiment and inherits our advanced “motion transfer” techniques from Gemini Robotics 1.5”
Source E7
Original source quotation: “We can now adapt to new bi-arm robot embodiments with just a few hours of adaptation time, typically with less than 200 examples”
Source E8
Original source quotation: “This works even with new embodiments with drastically different shapes, sensors and degrees of freedom”
Source E9
Original source quotation: “Gemini Robotics ER 2 now understands when tasks begin and end, and can pinpoint the moment key events occur”
Source E10
Original source quotation: “Furthermore, we are introducing multi-robot collaboration. This enables different types of robots to communicate and work together to solve complex workflows a single robot could not do alone”
Source E11
Original source quotation: “Gemini Robotics ER 2 is our safest robotics model to date in safety constraint following and human proximity benchmarks”
Source E12
Original source quotation: “It can better detect when humans are nearby, trigger safety tool calls and bring the robot to a safe stop if someone approaches too closely”
Source E13
Original source quotation: “Gemini Robotics 2 marks an important milestone on the path toward solving AGI in the physical world”
Source E14
Original source quotation: “Unlocking the true potential of robotics requires moving past single-task automation toward general-purpose intelligence”
Source E15
Source：Google DeepMind — Robotics · deepmind.google